Spanish Sentiment Analysis Using Universal Language Model Fine-Tuning: A Detailed Case of Study

Daniel Palomino, José Ochoa Luna

Abstract: Transfer Learning has emerged as one of the main image classification techniques for reusing architectures and weights trained on big datasets so as to improve small and specific classification tasks. In Natural Language Processing, a similar effect is obtained by reusing and transferring a language model. In particular, the Universal Language Fine-Tuning (ULMFiT) algorithm has proven to have an impressive performance on several English text classification tasks. In this paper, we aim at improving current state-of-the-art algorithms for Spanish Sentiment Analysis of short texts. In order to do so, we have adapted a ULMFiT algorithm to this setting. Experimental results on benchmark datasets show the potential of our approach.